AdaExploreBench：智能体主动探索能力新基准
AI 总结
arXiv 于 10 月 19 日刊出论文 AdaExploreBench，作者为 Rui Wang 等 18 人。该基准把环境动态设定为需要智能体主动取证并推断的隐藏规则，并在“隐式规则漂移”下让潜在规则无预告变化，要求智能体从性能下降中察觉旧知识失效并重新探索。作者称在八个领先大模型上的实验显示，主动且自适应的探索仍很困难：GPT-6 Sol 的校准准确率仅为 61.9%，而提供充分证据或去除规则漂移可使平均表现提升接近 10%。
深度见解
作者据此指出当前 LLM 智能体的关键瓶颈：拿到有效证据后往往能推理，但难以主动获取正确证据并识别已有证据何时失效。
Computer Science > Computation and Language
arXiv:2610.25950 (cs)
[Submitted on 19 Oct 2026]
Title:AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
Authors:Rui Wang, Zishen Lai, Jiayu Liu, Cheng Qian, Jeonghwan Kim, Heng Wang, Xuejun Zhang, Jiateng Liu, Bingxuan Li, Shujin Wu, Qing Zong, Tianshi Zheng, Chunyang Li, Qihan Lin, Chen Li, Dadi Guo, Xiusi Chen, Yangqiu Song
View a PDF of the paper titled AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments, by Rui Wang and 17 other authors